Evid Based Complement Alternat Med. 2021 Sep 23;2021:6637810. doi: 10.1155/2021/6637810. eCollection 2021.

ABSTRACT

Traditional Chinese drugs (TCDs) have been widely used in clinical practice in China and many other regions for thousands of years. Nowadays TCD's bioactive ingredients and mechanisms of action are being identified. However, the lack of standardized terminologies or ontologies for the description of TCDs has hindered the interoperability and deep analysis of TCD knowledge and data. By aligning with the Basic Formal Ontology (BFO), an ISO-approved top-level ontology, we constructed a community-driven TCD ontology (TCDO) with the aim of supporting standardized TCD representation and integrated analysis. TCDO provides logical and textual definitions of TCDs, TCD categories, and the properties of TCDs (i.e., nature, flavor, toxicity, and channel tropism). More than 400 popular TCD decoction pieces (TCD-DPs) and Chinese medicinal materials (CMMs) are systematically represented. The logical TCD representation in TCDO supports computer-assisted reasoning and queries using tools such as Description Logic (DL) and SPARQL queries. Our statistical analysis of the knowledge represented in TCDO revealed scientific insights about TCDs. A total of 36 TCDs with medium or high toxicity are most densely distributed, primarily in Aconitum genus, Lamiids clade, and Fabids clade. TCD toxicity is mostly associated with the hot nature and pungent or bitter flavors and has liver, kidney, and spleen channel tropism. The three pairs of TCD flavor-nature associations (i.e., bitter-cold, pungent-warm, and sweet-neutral) were identified. The significance of these findings is discussed. TCDO has also been used to support the development of a web-based traditional Chinese medicine semantic annotation system that provides comprehensive annotation for individual TCDs. As a novel formal TCD ontology, TCDO lays out a strong foundation for more advanced TCD studies in the future.

PMID:34603473 | PMC:PMC8483929 | DOI:10.1155/2021/6637810

Appl Clin Inform. 2021 Aug;12(4):910-923. doi: 10.1055/s-0041-1735180. Epub 2021 Sep 22.

ABSTRACT

OBJECTIVE: Verbal autopsy is a technique used to collect information about a decedent from his/her family members using questionnaires, conducting interviews, making observations, and sampling. In substantial parts of the world, particularly in Africa and Asia, many deaths are unrecorded. In 2017, globally pregnant women were dying daily around 810 and 295,000 in a year because of pregnancy-related problems, pointed out by World Health Organization. Identifying the cause of a death is a complex process which requires in-depth medical knowledge and practical experience. Generally, medical practitioners possess different knowledge levels, set of abilities, and problem-solving skills. Additionally, the medical negligence plays a significant part in further worsening the situation. Accurate identification of the cause of death can help a government to take strategic measures to focus on, particularly increasing the death rate in a specific region.

METHODS: This research provides a solution by introducing a semantic-based verbal autopsy framework for maternal death (SVAF-MD) to identify the cause of death. The proposed framework consists of four main components as follows: (1) clinical practice guidelines, (2) knowledge collection, (3) knowledge modeling, and (4) knowledge codification. Maternal ontology for the framework is developed using Protégé knowledge editor. Resource description framework application programming interface (API) for PHP (RAP) is used as a Semantic Web toolkit along with Simple Protocol and RDF Query Language (SPARQL) is used for querying with ontology to retrieve data.

RESULTS: The results show that 92% of maternal causes of deaths assigned using SVAF-MD correctly matched manual reports already prepared by gynecologists.

CONCLUSION: SVAF-MD, a semantic-based framework for the verbal autopsy of maternal deaths, assigns the cause of death with minimum involvement of medical practitioners. This research helps the government to ease down the verbal autopsy process, overcome the delays in reporting, and facilitate in terms of accurate results to devise the policies to reduce the maternal mortality.

PMID:34553359 | DOI:10.1055/s-0041-1735180

JMIR Pediatr Parent. 2021 Sep 19. doi: 10.2196/30169. Online ahead of print.

ABSTRACT

BACKGROUND: Parents commonly experience anxiety, worry and psychological distress in caring for newborn infants, particularly those born preterm. Web-based therapist services may offer greater accessibility and timely psychological support for parents, but are nevertheless labor-intensive due to their interactive nature. Chatbots that simulate human-like conversations show promise for such interactive applications.

OBJECTIVE: To explore the usability and feasibility of chatbot technology for gathering real-life conversation data on stress, sleep and infant feeding from parents with newborn infants and to investigate differences between experiences of parents with preterm and term infants.

METHODS: Parents aged ≥21 years with infants aged ≤6 months were enrolled from November 2018 to March 2019. Three chatbot scripts (stress, sleep, feeding) were developed to capture conversations with parents via their mobile devices. Parents completed a chatbot usability questionnaire upon study completion. Responses to closed-ended questions and manually-coded open-ended responses were summarized descriptively. Open-ended responses were analyzed using the Latent Dirichlet Allocation (LDA) method to uncover semantic topics.

RESULTS: Of 45 enrolled participants (20 preterm; 25 term), 26 completed the study. Parents rated the chatbot as "easy" to use (mean ± SD: 4.08±0.74; 1 [Very difficult] - 5 [Very easy]) and were "satisfied" (mean ± SD: 3.81±0.90; 1 [Very dissatisfied] - 5 [Very satisfied]). Of 45 enrolled parents, those with preterm infants reported emotional stress more frequently than parents of term infants (33 vs. 24 occasions). Parents generally reported satisfactory sleep quality. The preterm group reported feeding problems more frequently than the term group (8 vs. 2 occasions). In stress domain conversations, topics linked to "discomfort" and "tiredness" were more prevalent in preterm group conversations, whereas the topic of "positive feelings" occurred more frequently in term group conversations. Interestingly, feeding-related topics dominated the content of sleep domain conversations, suggesting that frequent or irregular feeding may affect parents' ability to get adequate sleep or rest.

CONCLUSIONS: The chatbot was successfully utilized to collect real-time conversation data on stress, sleep and infant feeding from a group of 45 parents. In their chatbot conversations, term group parents frequently expressed positive emotions, whereas preterm group parents frequently expressed physical discomfort and tiredness, as well as emotional stress. Overall, parents who completed the study gave positive feedback on their user experience with the chatbot as a tool to express their thoughts and concerns.

CLINICALTRIAL: ClinicalTrials.gov NCT03630679.

PMID:34544679 | DOI:10.2196/30169

Proc Int World Wide Web Conf. 2021 Apr;2021:2672-2683. doi: 10.1145/3442381.3450128. Epub 2021 Apr 19.

ABSTRACT

With 214 source vocabularies, the construction and maintenance process of the UMLS (Unified Medical Language System) Metathesaurus terminology integration system is costly, time-consuming, and error-prone as it primarily relies on (1) lexical and semantic processing for suggesting groupings of synonymous terms, and (2) the expertise of UMLS editors for curating these synonymy predictions. This paper aims to improve the UMLS Metathesaurus construction process by developing a novel supervised learning approach for improving the task of suggesting synonymous pairs that can scale to the size and diversity of the UMLS source vocabularies. We evaluate this deep learning (DL) approach against a rule-based approach (RBA) that approximates the current UMLS Metathesaurus construction process. The key to the generalizability of our approach is the use of various degrees of lexical similarity in negative pairs during the training process. Our initial experiments demonstrate the strong performance across multiple datasets of our DL approach in terms of recall (91-92%), precision (88-99%), and F1 score (89-95%). Our DL approach largely outperforms the RBA method in recall (+23%), precision (+2.4%), and F1 score (+14.1%). This novel approach has great potential for improving the UMLS Metathesaurus construction process by providing better synonymy suggestions to the UMLS editors.

PMID:34514472 | PMC:PMC8434895 | DOI:10.1145/3442381.3450128

Asian J Psychiatr. 2021 Aug 28;65:102820. doi: 10.1016/j.ajp.2021.102820. Online ahead of print.

ABSTRACT

BACKGROUND: Auditory emotion recognition (AER) deficits refer to the abnormal identification and interpretation of tonal or prosodic features that transmit emotional information in sounds or speech. Evidence suggests that AER deficits are related to the pathology of schizophrenia. However, the effect size of the deficit in specific emotional category recognition in schizophrenia and its association with psychotic symptoms have never been evaluated through a meta-analysis.

METHODS: A systematic search for literature published in English or Chinese until November 30, 2020 was conducted in PubMed, Embase, Web of Science, PsychINFO, and China National Knowledge Infrastructure (CNKI), WanFang and Weip Databases. AER differences between patients and healthy controls (HCs) were assessed by the standardized mean differences (SMDs). Subgroup analyses were conducted for the type of emotional stimuli and the diagnosis of schizophrenia or schizoaffective disorders (Sch/SchA). Meta-regression analyses were performed to assess the influence of patients' age, sex, illness duration, antipsychotic dose, positive and negative symptoms on the study SMDs.

RESULTS: Eighteen studies containing 615 psychosis (Sch/SchA) and 488 HCs were included in the meta-analysis. Patients exhibited moderate deficits in recognizing the neutral, happy, sad, angry, fear, disgust, and surprising emotion. Neither the semantic information in the auditory stimuli nor the diagnosis subtype affected AER deficits in schizophrenia. Sadness, anger, and disgust AER deficits were each positively associated with negative symptoms in schizophrenia.

CONCLUSIONS: Patients with schizophrenia have moderate AER deficits, which were associated with negative symptoms. Rehabilitation focusing on improving AER abilities may help improve negative symptoms and the long-term prognosis of schizophrenia.

PMID:34482183 | DOI:10.1016/j.ajp.2021.102820

J Ethnopharmacol. 2021 Sep 1:114588. doi: 10.1016/j.jep.2021.114588. Online ahead of print.

ABSTRACT

ETHNOPHARMACOLOGICAL RELEVANCE: Liver disease is a major cause of illness and death worldwide which accounts for approximately 2 million deaths per year worldwide, 1 million due to complications of cirrhosis and 1 million due to viral hepatitis and hepatocellular carcinoma. That's why it is seeking the researchers' attention to find out the effective treatment strategies. Phytochemicals from natural resources are the main leads for the development of noble hepatoprotective drugs. The majority of the natural sources whose active compounds are currently employed actually have an ethnomedical use. Ethnopharmacological research is essential for the development of these bioactive compounds. These studies not only provide scientific evidence on medicinal plants utilized for particular therapeutic purposes, but they also ensure cultural heritage preservation. Plenty of experimental studies have been well-documented that the ethnomedicinal plants are of therapeutics' interest for the advanced pharmacological intervention in terms of hepatic disorders.

AIM OF THE STUD: This study summarizes the processes of hepatotoxicity induced by various toxins and explores identified hepatoprotective plants and their phytoconstituents, which can guide the extraction of novel phytochemical constituents from plants to treat liver injury. This review aimed to summarize the hepatoprotective activity of Bangladeshi medicinal plants where the bioactive compounds may be leads for the drug discovery in future.

MATERIALS AND METHODS: Literature searches in electronic databases, such as Web of Science, Science Direct, SpringerLink, PubMed, Google Scholar, Semantic Scholar, Scopus, BanglaJOL, and so on, were performed using the keywords 'Bangladesh', 'ethnomedicinal plants', 'Hepatoprotective agents' as for primary searches, and secondary search terms were used as follows, either alone or in combination: traditional medicine, medicinal plants, folk medicine, liver, hepatitis, therapeutic uses, and anti-inflammatory. Besides, several books, including the book entitled "Medicinal plants of Bangladesh: chemical constituents and uses" authored by Abdul Ghani was carefully considered, which contained pharmacological properties and phytoconstituents of 449 medicinal plants growing and traditionally available in Bangladesh. Among them, the most promising plant species with their latest therapeutic effects against hepatic disorders were deeply considered in this review.

RESULTS: The results of this study revealed that in most cases, therapy using plant extracts stabilized altered hepatic biochemical markers induced by hepatotoxins. Initially, we investigated 32 plant species for hepatoprotective activity, however after extensive literature searching; we observed that 20 plants offer good pharmacological evidence of hepatoprotective function. Consequently, most bioactive compounds derived from the herbs including berberine, thymoquinone, andrographolide, ursolic acid, luteolin, naringenin, genistein, quercetin, troxerutin, morin, epigallocatechin-3-gallate, chlorogenic acid, emodin, curcumin, resveratrol, capsaicin, ellagic acid, etc. are appeared to be effective against hepatic disorders.

CONCLUSIONS: Flavonoids, phenolic acids, monoterpenoids, diterpenoids, triterpenoids, alkaloids, chromenes, capsaicinoids, curcuminoids, and anthraquinones are among the phytoconstituents were appraised to have hepatoprotective activities. All the actions displayed by these ethnomedicinal plants could make them serve as leads in the formulation of drugs with higher efficacy to treat hepatic disorders.

PMID:34480997 | DOI:10.1016/j.jep.2021.114588

Bioinformatics. 2021 Sep 3:btab627. doi: 10.1093/bioinformatics/btab627. Online ahead of print.

ABSTRACT

MOTIVATION: Metabolomics studies aim at reporting a metabolic signature (list of metabolites) related to a particular experimental condition. These signatures are instrumental in the identification of biomarkers or classification of individuals, however their biological and physiological interpretation remains a challenge. To support this task, we introduce FORUM: a Knowledge Graph (KG) providing a semantic representation of relations between chemicals and biomedical concepts, built from a federation of life science databases and scientific literature repositories.

RESULTS: The use of a Semantic Web framework on biological data allows us to apply ontological based reasoning to infer new relations between entities. We show that these new relations provide different levels of abstraction and could open the path to new hypotheses. We estimate the statistical relevance of each extracted relation, explicit or inferred, using an enrichment analysis, and instantiate them as new knowledge in the KG to support results interpretation/further inquiries.

AVAILABILITY: A web interface to browse and download the extracted relations, as well as a SPARQL endpoint to directly probe the whole FORUM knowledge graph, are available at https://forum-webapp.semantic-metabolomics.fr. The code needed to reproduce the triplestore is available at https://github.com/eMetaboHUB/Forum-DiseasesChem.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:34478489 | DOI:10.1093/bioinformatics/btab627

J Imaging. 2021 Jul 22;7(8):121. doi: 10.3390/jimaging7080121.

ABSTRACT

Cultural heritage images are among the primary media for communicating and preserving the cultural values of a society. The images represent concrete and abstract content and symbolise the social, economic, political, and cultural values of the society. However, an enormous amount of such values embedded in the images is left unexploited partly due to the absence of methodological and technical solutions to capture, represent, and exploit the latent information. With the emergence of new technologies and availability of cultural heritage images in digital formats, the methodology followed to semantically enrich and utilise such resources become a vital factor in supporting users need. This paper presents a methodology proposed to unearth the cultural information communicated via cultural digital images by applying Artificial Intelligence (AI) technologies (such as Computer Vision (CV) and semantic web technologies). To this end, the paper presents a methodology that enables efficient analysis and enrichment of a large collection of cultural images covering all the major phases and tasks. The proposed method is applied and tested using a case study on cultural image collections from the Europeana platform. The paper further presents the analysis of the case study, the challenges, the lessons learned, and promising future research areas on the topic.

PMID:34460757 | DOI:10.3390/jimaging7080121

Proceedings (IEEE Int Conf Bioinformatics Biomed). 2020 Dec;2020:1714-1719. doi: 10.1109/bibm49941.2020.9313375. Epub 2021 Jan 13.

ABSTRACT

A variety of severe health issues can be attributed to poor nutrition and poor eating behaviors. Research has explored the impact of nutritional knowledge on an individual's inclination to purchase and consume certain foods. This paper introduces the Ontology of Fast Food Facts, a knowledge base that models consumer nutritional data from major fast food establishments. This artifact serves as an aggregate knowledge base to centralize nutritional information for consumers. As a semantically-linked data source, the Ontology of Fast Food Facts could engender methods and tools to further the research and impact the health consumers' diet and behavior, which is a factor in many severe health outcomes. We describe the initial development of this ontology and future directions we plan with this knowledge base.

PMID:34457376 | PMC:PMC8389188 | DOI:10.1109/bibm49941.2020.9313375

J Biomed Inform. 2021 Aug 25:103897. doi: 10.1016/j.jbi.2021.103897. Online ahead of print.

ABSTRACT

INTRODUCTION: Existing methods to make data Findable, Accessible, Interoperable, and Reusable (FAIR) are usually carried out in a post-hoc manner: after the research project is conducted and data are collected. De-novo FAIRification, on the other hand, incorporates the FAIRification steps in the process of a research project. In medical research, data is often collected and stored via electronic Case Report Forms (eCRFs) in Electronic Data Capture (EDC) systems. By implementing a de-novo FAIRification process in such a system, the reusability and, thus, scalability of FAIRification across research projects can be greatly improved. In this study, we developed and implemented a novel method for de-novo FAIRification via an EDC system. We evaluated our method by applying it to the Registry of Vascular Anomalies (VASCA).

METHODS: Our EDC and research project independent method ensures that eCRF data entered into an EDC system can be transformed into machine-readable, FAIR data using a semantic data model (a canonical representation of the data, based on ontology concepts and semantic web standards) and mappings from the model to questions on the eCRF. The FAIRified data are stored in a triple store and can, together with associated metadata, be accessed and queried through a FAIR Data Point. The method was implemented in Castor EDC, an EDC system, through a data transformation application. The FAIRness of the output of the method, the FAIRified data and metadata, was evaluated using the FAIR Evaluation Services.

RESULTS: We successfully applied our FAIRification method to the VASCA registry. Data entered on eCRFs is automatically transformed into machine-readable data and can be accessed and queried using SPARQL queries in the FAIR Data Point. Twenty-one FAIR Evaluator tests pass and one test regarding the metadata persistence policy fails, since this policy is not in place yet.

CONCLUSION: In this study, we developed a novel method for de-novo FAIRification via an EDC system. Its application in the VASCA registry and the automated FAIR evaluation show that the method can be used to make clinical research data FAIR when they are entered in an eCRF without any intervention from data management and data entry personnel. Due to the generic approach and developed tooling, we believe that our method can be used in other registries and clinical trials as well.

PMID:34454078 | DOI:10.1016/j.jbi.2021.103897

Sensors (Basel). 2021 Aug 12;21(16):5435. doi: 10.3390/s21165435.

ABSTRACT

Indoor navigation systems incorporating augmented reality allow users to locate places within buildings and acquire more knowledge about their environment. However, although diverse works have been introduced with varied technologies, infrastructure, and functionalities, a standardization of the procedures for elaborating these systems has not been reached. Moreover, while systems usually handle contextual information of places in proprietary formats, a platform-independent model is desirable, which would encourage its access, updating, and management. This paper proposes a methodology for developing indoor navigation systems based on the integration of Augmented Reality and Semantic Web technologies to present navigation instructions and contextual information about the environment. It comprises four modules to define a spatial model, data management (supported by an ontology), positioning and navigation, and content visualization. A mobile application system was developed for testing the proposal in academic environments, modeling the structure, routes, and places of two buildings from independent institutions. The experiments cover distinct navigation tasks by participants in both scenarios, recording data such as navigation time, position tracking, system functionality, feedback (answering a survey), and a navigation comparison when the system is not used. The results demonstrate the system's feasibility, where the participants show a positive interest in its functionalities.

PMID:34450877 | DOI:10.3390/s21165435

PLoS One. 2021 Aug 26;16(8):e0256705. doi: 10.1371/journal.pone.0256705. eCollection 2021.

ABSTRACT

The huge amount of data made available by the massive usage of social media has opened up the unprecedented possibility to carry out a data-driven study of political processes. While particular attention has been paid to phenomena like elite and mass polarization during online debates and echo-chambers formation, the interplay between online partisanship and framing practices, jointly sustaining adversarial dynamics, still remains overlooked. With the present paper, we carry out a socio-semantic analysis of the debate about migration policies observed on the Italian Twittersphere, across the period May-November 2019. As regards the social analysis, our methodology allows us to extract relevant information about the political orientation of the communities of users-hereby called partisan communities-without resorting upon any external information. Remarkably, our community detection technique is sensitive enough to clearly highlight the dynamics characterizing the relationship among different political forces. As regards the semantic analysis, our networks of hashtags display a mesoscale structure organized in a core-periphery fashion, across the entire observation period. Taken altogether, our results point at different, yet overlapping, trajectories of conflict played out using migration issues as a backdrop. A first line opposes communities discussing substantively of migration to communities approaching this issue just to fuel hostility against political opponents; within the second line, a mechanism of distancing between partisan communities reflects shifting political alliances within the governmental coalition. Ultimately, our results contribute to shed light on the complexity of the Italian political context characterized by multiple poles of partisan alignment.

PMID:34437640 | PMC:PMC8389375 | DOI:10.1371/journal.pone.0256705

BMC Bioinformatics. 2021 Aug 25;22(Suppl 9):105. doi: 10.1186/s12859-021-04031-9.

ABSTRACT

BACKGROUND: Many systems biology studies leverage the integration of multiple data types (across different data sources) to offer a more comprehensive view of the biological system being studied. While SQL (Structured Query Language) databases are popular in the biomedical domain, NoSQL database technologies have been used as a more relationship-based, flexible and scalable method of data integration.

RESULTS: We have created a graph database integrating data from multiple sources. In addition to using a graph-based query language (Cypher) for data retrieval, we have developed a web-based dashboard that allows users to easily browse and plot data without the need to learn Cypher. We have also implemented a visual graph query interface for users to browse graph data. Finally, we have built a prototype to allow the user to query the graph database in natural language.

CONCLUSION: We have demonstrated the feasibility and flexibility of using a graph database for storing and querying immunological data with complex biological relationships. Querying a graph database through such relationships has the potential to discover novel relationships among heterogeneous biological data and metadata.

PMID:34433410 | DOI:10.1186/s12859-021-04031-9

PeerJ Comput Sci. 2021 Aug 3;7:e649. doi: 10.7717/peerj-cs.649. eCollection 2021.

ABSTRACT

Digital fraud has immensely affected ordinary consumers and the finance industry. Our dependence on internet banking has made digital fraud a substantial problem. Financial institutions across the globe are trying to improve their digital fraud detection and deterrence capabilities. Fraud detection is a reactive process, and it usually incurs a cost to save the system from an ongoing malicious activity. Fraud deterrence is the capability of a system to withstand any fraudulent attempts. Fraud deterrence is a challenging task and researchers across the globe are proposing new solutions to improve deterrence capabilities. In this work, we focus on the very important problem of fraud deterrence. Our proposed work uses an Intimation Rule Based (IRB) alert generation algorithm. These IRB alerts are classified based on severity levels. Our proposed solution uses a richer domain knowledge base and rule-based reasoning. In this work, we propose an ontology-based financial fraud detection and deterrence model.

PMID:34435097 | PMC:PMC8356649 | DOI:10.7717/peerj-cs.649

MethodsX. 2021 Jul 23;8:101460. doi: 10.1016/j.mex.2021.101460. eCollection 2021.

ABSTRACT

Despite the intense research activity in the last two decades, ontology integration still presents a number of challenging issues. As ontologies are continuously growing in number, complexity and size and are adopted within open distributed systems such as the Semantic Web, integration becomes a central problem and has to be addressed in a context of increasing scale and heterogeneity. In this paper, we describe a holistic alignment-based method for customized ontology integration. The holistic approach proposes additional challenges as multiple ontologies are jointly integrated at once, in contrast to most common approaches that perform an incremental pairwise ontology integration. By applying consolidated techniques for ontology matching, we investigate the impact on the resulting ontology. The proposed method takes multiple ontologies as well as pairwise alignments and returns a refactored/non-refactored integrated ontology that faithfully preserves the original knowledge of the input ontologies and alignments. We have tested the method on large biomedical ontologies from the LargeBio OAEI track. Results show effectiveness, and overall, a decreased integration cost over multiple ontologies.•OIAR and AROM are two implementations of the proposed method.•OIAR creates a bridge ontology, and AROM creates a fully merged ontology.•The implementation includes the option of ontology refactoring.

PMID:34434866 | PMC:PMC8374672 | DOI:10.1016/j.mex.2021.101460

Front Psychol. 2021 Aug 6;12:697550. doi: 10.3389/fpsyg.2021.697550. eCollection 2021.

ABSTRACT

Remote data collection procedures can strengthen developmental science by addressing current limitations to in-person data collection and helping recruit more diverse and larger samples of participants. Thus, remote data collection opens an opportunity for more equitable and more replicable developmental science. However, it remains an open question whether remote data collection procedures with children participants produce results comparable to those obtained using in-person data collection. This knowledge is critical to integrate results across studies using different data collection procedures. We developed novel web-based versions of two tasks that have been used in prior work with 4-6-year-old children and recruited children who were participating in a virtual enrichment program. We report the first successful remote replication of two key experimental effects that speak to the emergence of structured semantic representations (N = 52) and their role in inferential reasoning (N = 40). We discuss the implications of these findings for using remote data collection with children participants, for maintaining research collaborations with community settings, and for strengthening methodological practices in developmental science.

PMID:34421748 | PMC:PMC8377201 | DOI:10.3389/fpsyg.2021.697550

Artif Intell Med. 2021 Aug;118:102131. doi: 10.1016/j.artmed.2021.102131. Epub 2021 Jun 25.

ABSTRACT

Big data importance and potential are becoming more and more relevant nowadays, enhanced by the explosive growth of information volume that is being generated on the Internet in the last years. In this sense, many experts agree that social media networks are one of the internet areas with higher growth in recent years and one of the fields that are expected to have a more significant increment in the coming years. Similarly, social media sites are quickly becoming one of the most popular platforms to discuss health issues and exchange social support with others. In this context, this work presents a new methodology to process, classify, visualise and analyse the big data knowledge produced by the sociome on social media platforms. This work proposes a methodology that combines natural language processing techniques, ontology-based named entity recognition methods, machine learning algorithms and graph mining techniques to: (i) reduce the irrelevant messages by identifying and focusing the analysis only on individuals and patient experiences from the public discussion; (ii) reduce the lexical noise produced by the different ways in how users express themselves through the use of domain ontologies; (iii) infer the demographic data of the individuals through the combined analysis of textual, geographical and visual profile information; (iv) perform a community detection and evaluate the health topic study combining the semantic processing of the public discourse with knowledge graph representation techniques; and (v) gain information about the shared resources combining the social media statistics with the semantical analysis of the web contents. The practical relevance of the proposed methodology has been proven in the study of 1.1 million unique messages from >400,000 distinct users related to one of the most popular dietary fads that evolve into a multibillion-dollar industry, i.e., gluten-free food. Besides, this work analysed one of the least research fields studied on Twitter concerning public health (i.e., the allergies or immunology diseases as celiac disease), discovering a wide range of health-related conclusions.

PMID:34412847 | DOI:10.1016/j.artmed.2021.102131

J Biomed Semantics. 2021 Aug 9;12(1):15. doi: 10.1186/s13326-021-00246-0.

ABSTRACT

BACKGROUND: The ontology authoring step in ontology development involves having to make choices about what subject domain knowledge to include. This may concern sorting out ontological differences and making choices between conflicting axioms due to limitations in the logic or the subject domain semantics. Examples are dealing with different foundational ontologies in ontology alignment and OWL 2 DL's transitive object property versus a qualified cardinality constraint. Such conflicts have to be resolved somehow. However, only isolated and fragmented guidance for doing so is available, which therefore results in ad hoc decision-making that may not be the best choice or forgotten about later.

RESULTS: This work aims to address this by taking steps towards a framework to deal with the various types of modeling conflicts through meaning negotiation and conflict resolution in a systematic way. It proposes an initial library of common conflicts, a conflict set, typical steps toward resolution, and the software availability and requirements needed for it. The approach was evaluated with an actual case of domain knowledge usage in the context of epizootic disease outbreak, being avian influenza, and running examples with COVID-19 ontologies.

CONCLUSIONS: The evaluation demonstrated the potential and feasibility of a conflict resolution framework for ontologies.

PMID:34372934 | PMC:PMC8352153 | DOI:10.1186/s13326-021-00246-0

BMJ Open. 2021 Jul 23;11(7):e053402. doi: 10.1136/bmjopen-2021-053402.

ABSTRACT

OBJECTIVE: To examine inequalities in COVID-19 vaccination rates among elderly adults in England.

DESIGN: Cohort study.

SETTING: People living in private households and communal establishments in England.

PARTICIPANTS: 6 655 672 adults aged ≥70 years (mean 78.8 years, 55.2% women) who were alive on 15 March 2021.

MAIN OUTCOME MEASURES: Having received the first dose of a vaccine against COVID-19 by 15 March 2021. We calculated vaccination rates and estimated unadjusted and adjusted ORs using logistic regression models.

RESULTS: By 15 March 2021, 93.2% of people living in England aged 70 years and over had received at least one dose of a COVID-19 vaccine. While vaccination rates differed across all factors considered apart from sex, the greatest disparities were seen between ethnic and religious groups. The lowest rates were in people of black African and black Caribbean ethnic backgrounds, where only 67.2% and 73.8% had received a vaccine, with adjusted odds of not being vaccinated at 5.01 (95% CI 4.86 to 5.16) and 4.85 (4.75 to 4.96) times greater than the white British group. The proportion of individuals self-identifying as Muslim and Buddhist who had received a vaccine was 79.1% and 84.1%, respectively. Older age, greater area deprivation, less advantaged socioeconomic position (proxied by living in a rented home), being disabled and living either alone or in a multigenerational household were also associated with higher odds of not having received the vaccine.

CONCLUSION: Research is now urgently needed to understand why disparities exist in these groups and how they can best be addressed through public health policy and community engagement.

PMID:34301672 | PMC:PMC8313303 | DOI:10.1136/bmjopen-2021-053402

JMIR Med Inform. 2021 Jul 22;9(7):e30115. doi: 10.2196/30115.

ABSTRACT

BACKGROUND: Medical writing styles can have an impact on the understandability of health educational resources. Amid current web-based health information research, there is a dearth of research-based evidence that demonstrates what constitutes the best practice of the development of web-based health resources on children's health promotion and education.

OBJECTIVE: Using authoritative and highly influential web-based children's health educational resources from the Nemours Foundation, the largest not-for-profit organization promoting children's health and well-being, we aimed to develop machine learning algorithms to discriminate and predict the writing styles of health educational resources on children versus adult health promotion using a variety of health educational resources aimed at the general public.

METHODS: The selection of natural language features as predicator variables of algorithms went through initial automatic feature selection using ridge classifier, support vector machine, extreme gradient boost tree, and recursive feature elimination followed by revision by education experts. We compared algorithms using the automatically selected (n=19) and linguistically enhanced (n=20) feature sets, using the initial feature set (n=115) as the baseline.

RESULTS: Using five-fold cross-validation, compared with the baseline (115 features), the Gaussian Naive Bayes model (20 features) achieved statistically higher mean sensitivity (P=.02; 95% CI -0.016 to 0.1929), mean specificity (P=.02; 95% CI -0.016 to 0.199), mean area under the receiver operating characteristic curve (P=.02; 95% CI -0.007 to 0.140), and mean macro F1 (P=.006; 95% CI 0.016-0.167). The statistically improved performance of the final model (20 features) is in contrast to the statistically insignificant changes between the original feature set (n=115) and the automatically selected features (n=19): mean sensitivity (P=.13; 95% CI -0.1699 to 0.0681), mean specificity (P=.10; 95% CI -0.1389 to 0.4017), mean area under the receiver operating characteristic curve (P=.008; 95% CI 0.0059-0.1126), and mean macro F1 (P=.98; 95% CI -0.0555 to 0.0548). This demonstrates the importance and effectiveness of combining automatic feature selection and expert-based linguistic revision to develop the most effective machine learning algorithms from high-dimensional data sets.

CONCLUSIONS: We developed new evaluation tools for the discrimination and prediction of writing styles of web-based health resources for children's health education and promotion among parents and caregivers of children. User-adaptive automatic assessment of web-based health content holds great promise for distant and remote health education among young readers. Our study leveraged the precision and adaptability of machine learning algorithms and insights from health linguistics to help advance this significant yet understudied area of research.

PMID:34292167 | DOI:10.2196/30115